Views
No views yet
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|------------------------------------|---------|---------|-----------|---------|------------|------------|---------|
| rombodawg/Everyone-LLM-7b-Base | 70.21 | 66.38 | 86.02 | 64.94 | 57.89 | 80.43 | 65.58 |1models:
2 - model: cognitivecomputations_dolphin-2.6-mistral-7b-dpo
3 parameters:
4 weight: 1
5 - model: jondurbin_bagel-dpo-7b-v0.4
6 parameters:
7 weight: 1
8 - model: Locutusque_Hercules-2.0-Mistral-7B
9 parameters:
10 weight: 1
11 - model: Open-Orca_Mistral-7B-OpenOrca
12 parameters:
13 weight: 1
14 - model: teknium_OpenHermes-2.5-Mistral-7B
15 parameters:
16 weight: 1
17 - model: NousResearch_Nous-Capybara-7B-V1.9
18
19 parameters:
20 weight: 1
21 - model: Intel_neural-chat-7b-v3-3
22 parameters:
23 weight: 1
24 - model: mistralai_Mistral-7B-Instruct-v0.2
25 parameters:
26 weight: 1
27 - model: senseable_WestLake-7B-v2
28 parameters:
29 weight: 1
30 - model: defog_sqlcoder-7b
31 parameters:
32 weight: 1
33 - model: meta-math_MetaMath-Mistral-7B
34 parameters:
35 weight: 1
36 - model: nextai-team_apollo-v1-7b
37 parameters:
38 weight: 1
39 - model: WizardLM_WizardMath-7B-V1.1
40 parameters:
41 weight: 1
42 - model: openchat_openchat-3.5-0106
43 parameters:
44 weight: 1
45merge_method: task_arithmetic
46base_model: mistralai_Mistral-7B-v0.1
47parameters:
48 normalize: true
49 int8_mask: true
50dtype: float16
51| Metric | Value |
|---|---|
| Avg. | 70.21 |
| AI2 Reasoning Challenge (25-Shot) | 66.38 |
| HellaSwag (10-Shot) | 86.02 |
| MMLU (5-Shot) | 64.94 |
| TruthfulQA (0-shot) | 57.89 |
| Winogrande (5-shot) | 80.43 |
| GSM8k (5-shot) | 65.58 |